Starstruk Logo MarkStarstruk

v0.2.0

microsoft/graphragv0.2.0Jul 25, 2024by AlonsoGuevara

AI Summary

A minor release introducing prompt tuning enhancements and various fixes. It adds content-based KNN for few-shot examples, dynamic community report rating, and rate limiting. It also fixes several configuration and LLM connection issues.

Key Highlights

  • Added content-based KNN for selecting prompt tune few shot examples
  • Added dynamic community report rating to the prompt tuning engine
  • Added Minute-based Rate Limiting and fixed RPM/TPM settings
  • Added CLI flag to overlay default values onto a provided config
  • Fixed an issue where base OpenAI embeddings can't work with Azure OpenAI LLM

New Features

  • Added content-based KNN for selecting prompt tune few shot examples
  • Added dynamic community report rating to the prompt tuning engine
  • Added language support to prompt tuning
  • Added llm params to local and global search
  • Added N parameter support
  • Added support for non-open ai model config to prompt tune

Full Release Notes

## 0.2.0

- minor: Add content-based KNN for selecting prompt tune few shot examples
- minor: Add dynamic community report rating to the prompt tuning engine
- patch: Add Minute-based Rate Limiting and fix rpm, tpm settings
- patch: Add N parameter support
- patch: Add cli flag to overlay default values onto a provided config.
- patch: Add exception handling on file load
- patch: Add language support to prompt tuning
- patch: Add llm params to local and global search
- patch: Fix broken prompt tuning link on docs
- patch: Fix delta none on query calls
- patch: Fix docsite base url
- patch: Fix encoding model parameter on prompt tune
- patch: Fix for --limit exceeding the dataframe length
- patch: Fix for Ruff 0.5.2
- patch: Fixed an issue where base OpenAI embeddings can't work with Azure OpenAI LLM
- patch: Modify defaults for CHUNK_SIZE, CHUNK_OVERLAP and GLEANINGS to reduce time and LLM calls
- patch: fix community_report doesn't work in settings.yaml
- patch: fix llm response content is None in query
- patch: fix the organization parameter is ineffective during queries
- patch: remove duplicate file read
- patch: support non-open ai model config to prompt tune
- patch: use binary io processing for all file io operations


**Full Changelog**: https://github.com/microsoft/graphrag/compare/v0.1.1...v0.2.0